Dynamic generation of experimental treatment plans

Abstract

A farming machine is configured to autonomously operate in a field to accomplish a farming objective. While doing so the farming machine can dynamically modify treatment plans and/or generate experimental treatment plans. Dynamically modifying treatment plans includes modifying, delaying, accelerating, adding, and/or removing farming actions in a treatment plan. Generating an experimental treatment plan includes intentionally modifying a treatment plan to induce a variance in a result, measuring the result, and determining whether the result from the experimental treatment plan is better than the unmodified treatment plan. The farming machine is also configured to generate user interactable feedback, and receive user generated instruction, to dynamically modify treatment plans and/or generate experimental treatment plans.

What is claimed is: 
     
         1 . A method for generating an experimental treatment plan for an autonomous farming machine moving through a field comprising a plurality of field portions, the method comprising:
 performing prescribed treatments of a plant treatment plan comprising a sequence of prescribed treatments as the autonomous farming machine moves through the field;   generating an experimental treatment plan comprising a sequence of experimental treatments for the autonomous farming machine to apply to a subset of the plurality of field portions in the field, and wherein:
 the experimental treatment plan is configured to induce a variance between plants treated by the plant treatment plan and plants treated the experimental treatment plan, and 
 at least one experimental treatment in the experimental treatment plan is different from prescribed treatments of the plant treatment plan; 
   performing the experimental treatment plan for the subset of field portions; and   performing the plant treatment plan for a remainder of field portions of the plurality of field portions.   
     
     
         2 . The method of  claim 1 , further comprising:
 modifying the plant treatment plan for a subsequent season based on the experimental treatment plan.   
     
     
         3 . The method of  claim 2 , wherein modifying the plant treatment plan based on the experimental treatment plan further comprises:
 modifying the plant treatment plan such that prescribed treatments are not applied to the subset of field portions in the subsequent season.   
     
     
         4 . The method of  claim 2 , wherein modifying the plant treatment plan based on the experimental treatment plan further comprises:
 modifying the plant treatment plan such that one or more of the prescribed treatments is replaced with one or more of the experimental treatments of the experimental treatment plan for the subsequent season.   
     
     
         5 . The method of  claim 1 , further comprising:
 generating a second experimental treatment plan comprising a second sequence of second experimental treatments for the autonomous farming machine to apply to a second subset of the plurality of field portions in the field, wherein:
 at least one second experimental treatment in the second experimental treatment plan is different than prescribed treatments of the plant treatment plan and experimental treatments in the experimental treatment plan, 
 the second experimental treatment plan is configured to induce a second variance between plants treated by the plant treatment plan and plants treated with the second experimental treatment plan, 
 the variance induced by the experimental treatment plan is different from the second variance induced by the second experimental treatment plan, and 
 the second subset of the plurality of field portions is different than the subset of the plurality of field portions. 
   
     
     
         6 . The method of  claim 1 , further comprising:
 generating a plurality of experimental plant treatment plans for the autonomous farming machine to apply to a plurality of subsets of the plurality of field portions in the field, wherein
 each experimental treatment plan comprises at least one experimental treatment different than the experimental treatments of the other experimental treatment plans in the plurality of experimental plant treatment plans, 
 each experimental treatment plan is configured to induce a different variance from the other experimental treatment plans, and 
 each experimental treatment plan is applied to a different subset of the plurality of subsets of the plurality of field portions. 
   
     
     
         7 . The method of  claim 1 , further comprising:
 responsive to performing the experimental treatment plan for the subset of field portions and the prescribed treatment plan for the remainder of field portions:
 obtaining real-time measurements describing variance resulting from the experimental treatment plan in the subset of field portions; 
 obtaining real-time measurements describing variance resulting from the plant treatment plan in the remainder of field portions; and 
   determining an induced variance caused by the experimental treatment plan by comparing real-time measurements indicating plant variance for the experimental treatment plan and the plant treatment plan.   
     
     
         8 . The method of  claim 7 , wherein real-time measurements describing plant variance resulting from the experimental treatment plan and the real-time measurements describing plant change from the plant treatment plan are obtained on a subsequent pass of the autonomous farming machine through the field. 
     
     
         9 . The method of  claim 7 , further comprising:
 modifying one or more prescribed treatments in the plant treatment plan based on the induced variance cause by the experimental treatment plan.   
     
     
         10 . The method of  claim 1 , wherein the experimental treatment plan comprises at least one additional experimental treatment configured to be applied during a subsequent pass of the autonomous farming machine, and further comprising performing the at least one additional experimental treatment on the subsequent pass of the farming machine through the field. 
     
     
         11 . The method of  claim 1 , wherein generating the experimental treatment plan comprises:
 accessing an experimental field size describing an amount of the field allottable for the experimental treatment plan; and   wherein a size of the subset of field portions is less than the experimental field size.   
     
     
         12 . The method of  claim 1 , wherein generating the experimental treatment plan comprises generating experimental treatments for the experimental treatment plan less than a threshold level of dissimilarity away from prescribed treatments in the plant treatment plan. 
     
     
         13 . The method of  claim 1 , wherein generating the experimental treatment plan comprises identifying at least one row of plants in the field and the subset of field portions comprises the at least one row of plants. 
     
     
         14 . The method or  claim 1 , further comprising:
 transmitting, to a manager of the autonomous farming machine, the experimental treatment plan;   receiving, from the manager the autonomous farming machine, a verification to proceed with the experimental treatment plan; and   wherein the experimental treatment plan is applied to the subset of field portions responsive to receiving the verification.   
     
     
         15 . The method or  claim 1 , further comprising:
 transmitting, to a manager of the autonomous farming machine, the experimental treatment plan;   receiving, from the manager the autonomous farming machine, a verified subset of field portions for applying the experimental treatment plan; and   wherein the subset of field portions comprises the verified subset of field portions.
 responsive to receiving the verified subset of field portions from the manager. 
   
     
     
         16 . The method of  claim 1 , wherein generating the experimental treatment plan comprises:
 accessing an experimental area describing a location of the field allottable for the experimental treatment plan; and   wherein the subset of field portions is within the location in the field.   
     
     
         17 . The method of  claim 1 , wherein at least one experimental treatment of the experimental treatment plan is a different amount of treatment than a prescribed treatment in the plant treatment plan. 
     
     
         18 . The method of  claim 1 , wherein at least one experimental treatment of the experimental treatment plan is applied at a different location than a prescribed treatment in the plant treatment plan. 
     
     
         19 . The method of  claim 1 , wherein at least one experimental treatment of the experimental treatment plan is a different treatment type of treatment than a prescribed treatment of the plant treatment plan. 
     
     
         20 . The method of  claim 1 , wherein at least one experimental treatment of the experimental treatment plan employs a different machine configuration of the autonomous farming machine than a prescribed treatment of the plant treatment plan. 
     
     
         21 . The method of  claim 1 , wherein at least one experimental treatment of the experimental treatment plan is applied at a different precision than a prescribed treatment of the plant treatment plan. 
     
     
         22 . The method of  claim 1 , wherein the experimental treatment plan is generated in response to real-time measurements indicating that a plant quality is above a threshold plant quality. 
     
     
         23 . The method of  claim 1 , wherein the experimental treatment plan is generated in response to the real-time measurements indicating that a plant quality is below a threshold plant quality. 
     
     
         24 . The method of  claim 1 , wherein the experimental treatment plan is generated in response to the real-time measurements being a threshold level of dissimilarity away from an expected real-time measurement. 
     
     
         25 . The method of  claim 1 , further comprising:
 obtaining real-time measurements describing conditions of each of the plurality of field portions as the autonomous farming machine moves through the field performing prescribed treatments of the plant treatment plan; and   wherein the experimental treatment plan is generated based on the real time measurements.   
     
     
         26 . An autonomous farming machine configured for generating an experimental treatment plan to perform in a field a plurality of field portions, the farming machine comprising:
 a sensor array configured to obtain measurements of treatment plans executed in the field;   a treatment array configured to perform a plant treatment plan in the field;   one or more processors; and   a non-volatile computer readable storage medium storing computer program instructions for generating the experimental treatment plan, the computer program instructions when executed by the one or more processors causing the farming machine to:
 perform, using the treatment array, prescribed treatments of a plant treatment plan comprising a sequence of prescribed treatments as the autonomous farming machine moves through the field; 
 generating an experimental treatment plan comprising a sequence of experimental treatments for the autonomous farming machine to apply to a subset of the plurality of field portions in the field, and wherein:
 the experimental treatment plan is configured to induce a variance, measurable by the sensor array, between plants treated by the plant treatment plan and plants treated the experimental treatment plan, and 
 at least one experimental treatment in the experimental treatment plan is different from prescribed treatments of the plant treatment plan; 
 
 performing, using the treatment array, the experimental treatment plan for the subset of field portions; and 
 performing, using the treatment array, the plant treatment plan for a remainder of field portions of the plurality of field portions. 
   
     
     
         27 . A non-volatile computer readable storage medium storing computer program instructions for generating an experimental treatment plan, the computer program instructions when executed by the one or more processors causing the farming machine to:
 perform prescribed treatments of a plant treatment plan comprising a sequence of prescribed treatments as the autonomous farming machine moves through the field;   generate an experimental treatment plan comprising a sequence of experimental treatments for the autonomous farming machine to apply to a subset of the plurality of field portions in the field, and wherein:
 the experimental treatment plan is configured to induce a variance, measurable by the sensor array, between plants treated by the plant treatment plan and plants treated the experimental treatment plan, and 
 at least one experimental treatment in the experimental treatment plan is different from prescribed treatments of the plant treatment plan; 
   perform the experimental treatment plan for the subset of field portions; and   perform the plant treatment plan for a remainder of field portions of the plurality of field portions.